Isolater - Feed

Ax Jintao Zhang, Xuanyao Fong 17d ago

SHIELD: A Segmented Hierarchical Memory Architecture for Energy-Efficient LLM Inference on Edge NPUs

Memory architecture for efficient LLM inference on edge NPUs with optimized DRAM refresh for KV caches.

Ax Tatiana Petrova, Evgeny Polyachenko, Radu State 17d ago

Geometric Entropy and Retrieval Phase Transitions in Continuous Thermal Dense Associative Memory

Research on memory capacity of Hopfield networks using geometric constraints and phase transitions.

Ax Krisanu Sarkar 17d ago

Score Shocks: The Burgers Equation Structure of Diffusion Generative Models

Theoretical analysis of diffusion models using Burgers equation to understand score field evolution.

Ax Xiangru Jian, Hao Xu, Wei Pang, Xinjian Zhao, Chengyu Tao, Qixin Zhang, Xikun Zhang, Chao Zhang, Guanzhi Deng, Alex Xue, Juan Du, Tianshu Yu, Garth Tarr, Linqi Song, Qiuzhuang Sun, Dacheng Tao 17d ago

FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios

Benchmark dataset and evaluation for multimodal LLMs in manufacturing scenarios.

Ax Chao Zhang, Shuai Lin, ChengLei Dai, Ye Qian, Fan Mingyang, Yi Zhang, Yi Wang, Jingwei Zhuo 17d ago

Dual-Rerank: Fusing Causality and Utility for Industrial Generative Reranking

Industrial generative reranking system combining causality and utility for video search at scale.

Ax Yogesh Phalak, Wen Sin Lor, Apoorva Khairnar, Benjamin Jantzen, Noel Naughton, Suyi Li 17d ago

OpenPRC: A Unified Open-Source Framework for Physics-to-Task Evaluation in Physical Reservoir Computing

Open-source framework for evaluating physical reservoir computing systems across various substrates.

Ax Dustin Bryant, Jonathan Juli\'an Huerta y Munive, Cezary Kaliszyk, Josef Urban 17d ago

Munkres' General Topology Autoformalized in Isabelle/HOL

LLM-based coding agents formalized 85K lines of topology proofs in Isabelle/HOL using ChatGPT and Claude.

Ax Yu Liang, Liangxin Liu, Longzheng Wang, Yan Wang, Yueyang Zhang, Long Xia, Zhiyuan Sun, Daiting Shi 17d ago

ConsistRM: Improving Generative Reward Models via Consistency-Aware Self-Training

Paper on generative reward models for LLM alignment using consistency-aware self-training to improve scalability.

Ax Shlomi Hod, Debanuj Nayak, Jason R. Gantenberg, Iden Kalemaj, Thomas A. Trikalinos, Adam Smith 17d ago

Differentially Private Modeling of Disease Transmission within Human Contact Networks

Research on differentially private disease transmission models in contact networks using machine learning.

Ax Lech Madeyski 17d ago

Triage: Routing Software Engineering Tasks to Cost-Effective LLM Tiers via Code Quality Signals

Privacy-preserving epidemiologic modeling of disease transmission in contact networks using differential privacy.

Ax Jorge Alda 17d ago

Lecture notes on Machine Learning applications for global fits

Semi-autonomous multi-agent system for small molecule drug discovery using multi-modal AI agents and GNNs trained on 800M molecules.

Ax Ravindra Ganti, Steve Xu 17d ago

From LLM to Silicon: RL-Driven ASIC Architecture Exploration for On-Device AI Inference

RL-driven compiler using Soft Actor-Critic to jointly optimize ASIC architecture, memory hierarchy, and workload partitioning for on-device AI inference across technology nodes.

Ax F. Fernando Jurado-Lasso, J. F. Jurado 17d ago

RL-ASL: A Dynamic Listening Optimization for TSCH Networks Using Reinforcement Learning

Reinforcement learning optimization for TSCH MAC protocol in IoT networks to reduce idle listening and power consumption under dynamic traffic conditions.

Ax Michael Cuccarese 17d ago

Predicting Activity Cliffs for Autonomous Medicinal Chemistry

ML approach to predict activity cliffs in medicinal chemistry by identifying structural modifications that cause large potency shifts using ChEMBL molecular pair data.

Ax Tunazzina Islam 17d ago

Reasoning-Based Refinement of Unsupervised Text Clusters with LLMs

Framework using LLMs as semantic judges to validate and restructure outputs from unsupervised text clustering methods, improving coherence and grounding without labeled data.

Ax Mohamed Ehab (Faculty of Computer Science, October University for Modern Science & Arts, Giza, Egypt), Ali Hamdi (Faculty of Computer Science, October University for Modern Science & Arts, Giza, Egypt), Khaled Shaban (Department of Computer Science and Engineering, Qatar University, Doha, Qatar) 17d ago

CAMO: A Class-Aware Minority-Optimized Ensemble for Robust Language Model Evaluation on Imbalanced Data

CAMO is an ensemble technique for imbalanced text classification that optimizes minority class performance through hierarchical voting, confidence calibration, and uncertainty estimation.

Ax Robert Chew, Stephanie Eckman, Christoph Kern, Frauke Kreuter 17d ago

From Ground Truth to Measurement: A Statistical Framework for Human Labeling

Framework for understanding systematic variation in human-labeled training data, distinguishing between ambiguous items, divergent interpretations, and mistakes rather than treating all disagreement as noise.

Ax Mohammad Siavashi, Mariano Scazzariello, Gerald Q. Maguire Jr., Dejan Kosti\'c, Marco Chiesa 17d ago

Blink: CPU-Free LLM Inference by Delegating the Serving Stack to GPU and SmartNIC

Blink is an LLM serving architecture that removes the host CPU from the critical path by delegating orchestration and token control to GPU and SmartNIC, improving inference performance and datacenter resource utilization.

Ax Ziyi Wang, Siva Rajesh Kasa, Ankith M S, Santhosh Kumar Kasa, Jiaru Zou, Sumit Negi, Ruqi Zhang, Nan Jiang, Qifan Song 17d ago

DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification

DIVERSED: relaxed speculative decoding for LLM inference using dynamic ensemble verification to improve token acceptance rates.

Ax Lingqing Shen, Fatma K{\i}l{\i}n\c{c}-Karzan 17d ago

Parameter-free non-ergodic extragradient algorithms for solving monotone variational inequalities

Parameter-free extragradient algorithms for monotone variational inequalities without manual stepsize selection.

Ax Jonah Botvinick-Greenhouse, Yunan Yang 17d ago

On the Unique Recovery of Transport Maps and Vector Fields from Finite Measure-Valued Data

Theoretical guarantees for unique recovery of transport maps and vector fields from finite measure-valued data.

Ax Zaid Ghazal, Hadiza Yusuf, Khouloud Gaaloul 17d ago

Towards Counterfactual Explanation and Assertion Inference for CPS Debugging

Debugging techniques for cyber-physical systems using counterfactual explanations and assertion inference.

Ax David Gringras 17d ago

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures

IatroBench: pre-registered study documenting how AI safety measures can cause harmful model behavior changes in medical advice contexts.

Ax Swarnadip Chatterjee, Vladimir Basic, Arrigo Capitanio, Orcun Goksel, Joakim Lindblad 17d ago

Needle in a Haystack -- One-Class Representation Learning for Detecting Rare Malignant Cells in Computational Cytology

One-class representation learning approach for detecting rare malignant cells in computational cytology using weakly supervised methods.

Ax Cathy Jiao, Juan Elenter, Praveen Ravichandran, Bernd Huber, Joseph Cauteruccio, Todd Wasson, Timothy Heath, Chenyan Xiong, Mounia Lalmas, Paul Bennett 17d ago

Efficient Dataset Selection for Continual Adaptation of Generative Recommenders

Dataset selection strategies for continual adaptation of generative recommenders under temporal distributional drift.

Ax Romano Li, Jianfei Cao 17d ago

The Condition-Number Principle for Prototype Clustering

Geometric framework linking objective accuracy to structural recovery in prototype-based clustering via condition numbers.

Ax Pei-Xi Xie, Che-Yu Lin, Cheng-Lin Yang 17d ago

Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing

Methods to mitigate distribution sharpening in math RLVR through hint synthesis and annealing strategies.

Ax Haiyan Du, Hu Yang 17d ago

Sparse $\epsilon$ insensitive zone bounded asymmetric elastic net support vector machines for pattern classification

Sparse epsilon-insensitive elastic net SVM variant for noise-robust pattern classification with improved sparsity.

Ax Xiangyue Liu, Zijian Zhang, Miles Yang, Zhao Zhong, Liefeng Bo, Ping Tan 17d ago

Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding

Symbiotic-MoE: unified pre-training framework enabling Large Multimodal Models to generate images while maintaining understanding capabilities.

Ax Manoj Chandrashekar Rao 17d ago

Sensitivity-Positional Co-Localization in GQA Transformers

LSLoRA: investigation of sensitivity-positional co-localization in GQA transformers, restricting LoRA to optimally sensitive layers.

Ax Tong Duy Son, Kohta Sugiura, Marc Brughmans, Andrey Hense, Zhihao Liu, Amirthalakshmi Veeraraghavan, Ajinkya Bhave, Jay Masters, Paolo di Carlo, Theo Geluk 17d ago

Toward Generalizable Graph Learning for 3D Engineering AI: Explainable Workflows for CAE Mode Shape Classification and CFD Field Prediction

Graph learning framework for 3D engineering AI applications including CAE and CFD predictions with explainability.

Ax Chanhyuk Choi, Taesoo Kim, Donggyu Lee, Siyeol Jung, Taehwan Kim 17d ago

Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video

Cross-modal emotion transfer technique for emotion editing in synthetic talking face videos using generative models.

Ax Xinshun Feng, Xinhao Song, Lijun Li, Gongshen Liu, Jing Shao 17d ago

SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents

SEARL: framework for self-evolving AI agents that jointly optimize policy and tool graphs to learn from trajectories without large-scale LLMs.

Ax Ivan Lau, Jonathan Scarlett 17d ago

Order-Optimal Sequential 1-Bit Mean Estimation in General Tail Regimes

Theoretical research on mean estimation under 1-bit communication constraints using adaptive randomized thresholds.

Ax Kaiyuan Tian, Yu Tang, Gongqingjian Jiang, Baihui Liu, Yifu Gao, Xialin Su, Linbo Qiao, Dongsheng Li 17d ago

GRASS: Gradient-based Adaptive Layer-wise Importance Sampling for Memory-efficient Large Language Model Fine-tuning

GRASS: gradient-based method for memory-efficient LLM fine-tuning using adaptive layer-wise importance sampling, balancing efficiency with model expressiveness.

Ax Giulio Valentino Dalla Riva, Matteo Dalla Riva 17d ago

Intensity Dot Product Graphs

Intensity Dot Product Graphs extending random dot product graphs with Poisson point process for latent positions.

Ax Praveen Kumar Menaka Sekar, Ion Matei, Maksym Zhenirovskyy, Hon Yung Wong, Sayuri Kohmura, Shinji Hotta, Akihiro Inomata 17d ago

Automatic Generation of Executable BPMN Models from Medical Guidelines

Pipeline converting healthcare policy documents to executable BPMN models using LLMs for policy simulation and evaluation.

Ax Harsh Kohli, Srinivasan Parthasarathy, Huan Sun, Yuekun Yao 17d ago

Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers

Recurrent-depth transformers enabling iterative reasoning to improve multi-hop knowledge composition in language models.

Ax Jannik Nitschke, Lukas Wegmeth, Joeran Beel 17d ago

Ensembles at Any Cost? Accuracy-Energy Trade-offs in Recommender Systems

Study of accuracy-energy trade-offs in ensemble recommender systems across 93 experiments comparing multiple models to single models.

Ax Kun Gao, Davide Sold\`a, Thomas Eiter, Katsumi Inoue 17d ago

Visual Perceptual to Conceptual First-Order Rule Learning Networks

Learns first-order rules from image data without labels, automatically inventing predicates for explainable AI and enhancing LLM reasoning.

Ax Nickson Patel 17d ago

Dynamic Attentional Context Scoping: Agent-Triggered Focus Sessions for Isolated Per-Agent Steering in Multi-Agent LLM Orchestration

DACS mechanism for multi-agent LLM orchestration isolating per-agent context via registry and focus session modes to prevent context pollution.

Ax Tao Hana, Zhibin Wen, Zhenghao Chen, Fenghua Lin, Junyu Gao, Song Guo, Lei Bai 17d ago

Generative 3D Gaussian Splatting for Arbitrary-ResolutionAtmospheric Downscaling and Forecasting

GSSA-ViT framework using 3D Gaussian splatting for arbitrary-resolution weather forecasting and downscaling of atmospheric fields.

Ax Shiwan Zhao, Zhihu Wang, Xuyang Zhao, Jiaming Zhou, Caiyue Xu, Chenfei Liu, Liting Zhang, Yuhang Jia, Yanzhe Zhang, Hualong Yu, Zichen Xu, Qicheng Li, Yong Qin 17d ago

Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning

Unified framework viewing LLM post-training methods (SFT, preference optimization, RL, distillation) through off-policy and on-policy learning perspectives.

Ax Ryo Suzuki, Shohei Watabe 17d ago

Investigation of Automated Design of Quantum Circuits for Imaginary Time Evolution Methods Using Deep Reinforcement Learning

Uses deep reinforcement learning to automatically design quantum circuits for variational imaginary time evolution on NISQ devices.

Ax Yuanjian Xu, Tianze Sun, Changwei Xu, XinLong Zhao, Jianing Hao, Ran Chen, Yang Liu, Ruijie Xu, Stephen Chen, Guang Zhang 17d ago

Rethinking Data Mixing from the Perspective of Large Language Models

Studies data mixing strategies for LLM training, questioning domain definitions, human-model alignment, and impact of domain weighting on generalization.

Ax Alin-Gabriel V\u{a}duva, Simona-Vasilica Oprea, Adela B\^ara 17d ago

Are we still able to recognize pearls? Machine-driven peer review and the risk to creativity: An explainable RAG-XAI detection framework with markers extraction

Discusses risks of LLM-generated peer reviews and automated editorial processes, proposing RAG-XAI detection framework for identifying machine-generated content.

Ax Gyanendra Das, Sai Satyam Jena 17d ago